Integrated Image-Text Based on Semi-supervised Learning for Small Sample Instance Segmentation

TL;DR

This paper introduces a semi-supervised learning approach for small sample instance segmentation that leverages unlabeled data and integrates image-text features to improve accuracy and reduce pre-training reliance.

Contribution

The method combines pseudo-label generation and image-text feature integration, enhancing small sample segmentation without extensive pre-training or additional annotation.

Findings

Improves segmentation accuracy across diverse datasets.

Reduces dependence on pre-training datasets.

Enhances classification confidence with image-text integration.

Abstract

Small sample instance segmentation is a very challenging task, and many existing methods follow the training strategy of meta-learning which pre-train models on support set and fine-tune on query set. The pre-training phase, which is highly task related, requires a significant amount of additional training time and the selection of datasets with close proximity to ensure effectiveness. The article proposes a novel small sample instance segmentation solution from the perspective of maximizing the utilization of existing information without increasing annotation burden and training costs. The proposed method designs two modules to address the problems encountered in small sample instance segmentation. First, it helps the model fully utilize unlabeled data by learning to generate pseudo labels, increasing the number of available samples. Second, by integrating the features of text and image, more accurate classification results can be obtained. These two modules are suitable for box-free and box-dependent frameworks. In the way, the proposed method not only improves the performance of small sample instance segmentation, but also greatly reduce reliance on pre-training. We have conducted experiments in three datasets from different scenes: on land, underwater and under microscope. As evidenced by our experiments, integrated image-text corrects the confidence of classification, and pseudo labels help the model obtain preciser masks. All the results demonstrate the effectiveness and superiority of our method.